Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical values relating to increases

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to financial or quantitative increases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bowman
    -0.62
    mates
    -0.60
     Deer
    -0.60
    mate
    -0.60
    rome
    -0.60
     Circus
    -0.59
    got
    -0.56
    icism
    -0.56
    zan
    -0.56
     Cannes
    -0.55
    POSITIVE LOGITS
    xual
    1.07
    over
    0.90
    itial
    0.83
    onential
    0.79
     subsequ
    0.78
    itures
    0.74
     averaging
    0.72
     rate
    0.71
    jriwal
    0.70
    inth
    0.69
    Act Density 0.078%

    No Known Activations